GPT Image 2 prompts

Subject: A room with dappled sunlight.

Main Subject: A 4:3 landscape indoor portrait. A {argument name="person" default="woman in her 20s"} sits on the right side of the frame, in a near full-body composition from her upper body to her feet. The person occupies about half of the entire frame, extending her legs to the front left to create a diagonal line. On the left are {argument name="background items" default="bookshelves and a record rack"}, and on the right are an aquarium and a wooden table, creating a space like a small Japanese-style atelier by the window.

Person/Expression: Bright ivory-beige toned fair skin, with a smooth texture containing a hint of pink flush. Soft highlights fall on the cheeks, tip of the nose, shoulders, collarbone, and knees, preserving natural skin grain. Precise and elegant doll-like Japanese makeup. Pale rose pink blush, champagne beige and pink-brown eye shadow, long thin eyelashes, natural tear bags, light brown soft eyebrows, and a translucent pink-beige gloss lip. Small clear catchlights in the eyes. Facing slightly towards the top left, with a quiet expression as if looking up at the light from the window.

Clothing/Pose: Hair is bright milk tea ash brown. Thin see-through bangs, layer cut along the face, medium-long reaching below the shoulders. Hair ends are loosely curled inward, with fine highlights and natural loose hairs meticulously depicted. Clothing is an {argument name="clothing" default="off-white ivory ribbed camisole"}. Thin shoulder straps, subtle lace at the chest, and a mature silhouette that naturally follows the body. Bottoms are matching soft shorts. Barefoot, no loose socks. The right hand rests on a cushion behind the body for support, and the left arm is placed naturally at the side of the waist. Knees are slightly bent, with feet lightly touching the record rack at the front left.

Background/Lighting: An afternoon sun, not too strong, shines through an old wooden window frame into a warm Japanese-style vintage room. To the left are wooden bookshelves, paperbacks, records, old musical instruments, and a round mirror ball. In the back are wooden boxes, plants, and an unreadable blue label. To the right are a transparent aquarium, goldfish, aquatic plants, glass reflections, an antique-style camera, and dried flowers. Green bokeh outside the window. The primary light enters from the window in the background, edging the hair, cheeks, shoulders, and knees. Inside, soft reflected light lifts the shadows, casting fine dappled sunlight patterns on the blankets and wood grain.

Composition/Camera: A natural camera position looking down diagonally from a slightly elevated viewpoint. 35mm to 50mm equivalent lens feel. Focus on the face and upper body, with foreground records and background greenery lightly blurred. Depth is created by the diagonal lines of the legs, vertical lines of the window frame, and the left-right framing of the bookshelf and aquarium. Shallow depth of field as if taken with a professional camera.

Texture/Style: Realistic photographic expression. Meticulously depicts warm film-like tones, soft highlights, natural skin texture, fine hair strands, wood and fabric grain, and the transparency of the glass aquarium. Finished like a calm magazine photo rather than excessive skin correction.

Theme: {argument name="theme" default="Dissolving on the water surface"}\n\nSubject: A vertical {argument name="aspect ratio" default="2:3"} photograph. An adult woman in a {argument name="outfit" default="white bikini"} is relaxing on a large, transparent, glittery floatie. The person is positioned slightly to the left of the center, occupying about half of the frame, with a cool composition utilizing the turquoise blue water surface and wide upper margin.\n\nPerson/Expression: Natural and realistic refined facial features. Dark brown hair tied in a high, rough bun, with thin bangs and loose strands around the face. Transparent natural makeup, pale coral pink cheeks and lips. Face turned slightly to the right of the screen, looking at the camera with a gentle smile. Shoulders and expression relaxed, creating a calm holiday atmosphere.\n\nClothing/Pose: An ivory white string bikini with thin straps and subtle gathers. The upper body is tilted diagonally towards the back of the floatie, with the back and waist softly supported. The person's right elbow is on the edge of the floatie, with the right hand lightly touching near the temple. The left arm is naturally lowered along the front floatie, with fingertips relaxed. Both legs are lightly bent, with one leg in front and the other layered behind, extending so that from the knees down they are naturally cropped at the right edge of the screen. Accurately express the sinking of the floatie, contact with the body, and water droplets on wet skin.\n\nBackground/Light: Bright, minimal outdoor pool. Foreground features a transparent floatie reflecting light and fine water ripples, middle ground is clear blue water, and background consists of cream-beige plastered walls and a white poolside. A white large planter and slender palm are placed in the upper right, with leaf shadows cast on the wall. Warm sunlight enters from the top left of the screen, brightly illuminating the hair, shoulders, arms, and top of the thighs. Pale blue reflected light from the water surface wraps around to the shaded side of the skin, with shadows flowing softly to the bottom right.\n\nComposition/Camera: Vertical position, medium-long shot from a slightly high eye level. The person's face is toward the top left of the screen, and the floatie crosses the bottom half of the screen significantly. Leave wide margins for the wall and water at the top, creating stability with the diagonal body lines and the circle of the floatie. Natural compression feel of around 85mm, focusing on the face and upper body, with the background slightly and softly blurred.\n\nTexture/Style: A clean, realistic resort portrait. Bright high-key tone, low contrast, refreshing color scheme centered on ivory and aqua blue. Maintain natural skin texture, delicately depicting fine water droplets on wet skin, reflections on transparent vinyl, blue glitter, and water ripples. Avoid excessive skin correction, aiming for an elegant and light finish like a magazine photo.\n\nNegative: Underage-looking persons, unnatural faces, unnatural gaze, extra fingers, missing fingers, fused limbs, broken joints, twisted legs, poor contact with the floatie, floating body, unnatural gravity, incorrect perspective, shadows inconsistent with light source, overexposure, transparent swimwear, text, logo, watermark, plastic-like skin.

Ultra-photorealistic luxury fashion editorial, premium studio campaign, a beautiful young Korean woman with flawless porcelain skin, delicate facial features, naturally glossy lips, expressive almond-shaped eyes, and long voluminous soft-wave dark hair. She wears an elegant deep mocha-brown satin halter-neck draped blouse with luxurious fluid silk texture, paired with impeccably tailored high-waisted wide-leg chocolate trousers, pointed dark-brown leather stilettos, a minimalist luxury wristwatch, delicate gold earrings, and carries a structured premium dark leather handbag. She is captured in a powerful full-body confident runway walk directly toward the camera. One hand is casually inside the trouser pocket while the other naturally holds the handbag. Long graceful stride, straight posture, relaxed shoulders, elongated neck, confident fashion-model body language, subtle editorial expression, calm luxury attitude, eyes looking slightly upward and away from the camera, cinematic elegance. Shot inside a minimalist premium mocha luxury photography studio with a seamless matte brown infinity backdrop, polished reflective floor, subtle atmospheric haze, and a perfectly centered warm circular spotlight glow behind the model creating a luxurious halo effect. The environment is clean, uncluttered, and highly realistic with no props except the handbag. Lighting: large overhead octabox as key light, soft front beauty fill, warm golden backlight creating a subtle halo around the hair, gentle rim lighting defining the silhouette, realistic soft shadows, premium commercial studio lighting, luxury perfume campaign aesthetic. Color grading: rich mocha brown palette, warm bronze highlights, deep chocolate shadows, cinematic HDR contrast, natural skin tones, subtle filmic richness, premium Vogue editorial look, extremely realistic reflections and fabric texture. Camera: full-body vertical composition, eye-level perspective, 85mm lens, f/2.8, shallow depth of field, razor-sharp facial details, ultra-clean skin texture, realistic hair strands, physically accurate fabric folds, luxury commercial fashion photography. Hyper-realistic, ultra-detailed, true-to-life, 8K HDR, professional fashion photoshoot, Vogue cover quality, Hasselblad medium-format realism, flawless anatomy, natural proportions, premium luxury campaign, no text, no watermark, no logo, no extra people.

以上传人像作为唯一人物参考，生成一组5张独立的美式西部牛仔风时尚大片，不拼图。保持人物五官、脸型和气质一致，长卷黑发，自然真实，不僵硬、不变脸。

Create a polished square promotional cover image for {argument name="app name" default="Highlighted"}, showing a modern iPhone standing upright at a slight angle on a bright white desk, with a clean productivity-and-reading aesthetic. On the phone screen, display a minimalist gallery grid of exactly 12 saved highlight cards arranged in 3 columns by 4 rows, each with a small gray label line beneath it; the cards show varied bookish visuals such as a classical portrait, yellow notebook, framed photo, white note with cord, red-and-yellow abstract cover, pencil illustration, dark statue face, blue night cover, beige dotted page, pale sails, ocean water, and a balloon landscape. At the bottom of the phone UI, include a large rounded blue add button with a white plus sign. Surround the phone with translucent floating feature widgets: on the left, one pill-shaped toolbar with exactly 5 elements—a paper-plane/filter icon and 4 circular color swatches in white, light gray, black, and navy; on the upper right, one glassmorphism audio card with a play button and 5 horizontal transcript lines including 2 yellow highlight lines; in the middle right, one frosted audio waveform card with a glowing circular orb and blue waveform; on the lower right, one frosted action toolbar with exactly 5 icons—a document, chevron arrow, share, cloud upload, and envelope. Desk props include a white tray of folders with a green spreadsheet document icon on the left, a small stack of pastel sticky notes in the foreground, an open book with yellow highlighted text at bottom right, loose papers with highlighted passages, and a stack of hardcover books on the right. Use soft natural window light, shallow depth of field, realistic high-end product photography, creamy whites and warm neutrals, subtle shadows, glassy translucent UI overlays, crisp phone details, no visible brand logos except the app-like interface, no watermark, no extra text beyond simple UI marks. Use a premium launch-promo composition suitable for an in-app event cover, {argument name="image aspect ratio" default="1:1 square"}.

Create a photorealistic close-up beauty portrait of {argument name="subject" default="a young East Asian woman with natural skin and short wet black hair tucked behind one ear"} against a matching patterned backdrop. She is bare-shouldered, framed from the upper chest upward, turned slightly three-quarters toward the camera, with her chin gently resting on her right hand and a calm, soft, direct gaze. Project a crisp ornamental light pattern across her face, neck, shoulder, hand, and the background: {argument name="projected pattern" default="repeating soft-edged pentagon and hexagon tile motifs with coral-red and muted blue circular centers, like sunlight passing through a decorative screen"}. The pattern should align naturally over facial contours and skin, creating realistic shadows and highlights rather than painted-on makeup. Use {argument name="lighting" default="warm late-afternoon sunlight with high contrast but soft skin detail"}, shallow depth of field, glossy eyes, subtle peach lips, minimal makeup, and fine realistic hair strands. The mood is serene, intimate, editorial, and cinematic, with a color palette of warm beige skin tones, coral red accents, dusty blue shadows, and cream highlights. Vertical portrait composition, 4:5 aspect ratio, ultra-detailed skin texture, natural imperfections, no text, no watermark, no extra people, no jewelry, no clothing distractions.

Goal: Create a warm children’s picture-book style 4-panel comic about a family of cute ducklings traveling internationally to reunite with their parent, using watercolor-and-colored-pencil textures on aged cream paper.

Canvas: Square 1:1 image, arranged as a 2×2 comic grid with thick hand-drawn black panel borders. Add colored pencil tips around the outer left and right edges like an art-table border. Use a cozy illustrated travel-journal look, detailed but soft, with visible paper grain, ink outlines, pastel colors, and expressive cartoon faces.

Main characters: Show exactly 4 duck family members throughout the story: 1 larger parent duck wearing a black leather jacket, white shirt, gold necklace, and carrying or standing near brown luggage; 1 young duckling with a red scarf and a small blue rolling suitcase with a teddy bear visible; 1 young duckling with a pink bow and pink dress holding a plush toy; and 1 second larger parent duck appearing in the final reunion panel. All ducks are fluffy white/yellow, with orange beaks and feet, rosy cheeks, and childlike rounded proportions.

Panel 1, top left: Title text in bold hand-lettered uppercase: “{argument name="first panel title" default="SHANGHAI TO TOKYO"}”. Under it, two label strips: “{argument name="first departure label" default="EARLY DEPARTURE"}” and “4:30 AM”. Night airport scene in Shanghai with a dark blue starry sky, runway, terminal windows, a plane, and the Shanghai skyline including a tall tower in the background. Add a dark airport sign with an airplane icon reading “SHANGHAI PVG → TOKYO NRT”. The leather-jacket parent walks with the two ducklings and luggage. Include exactly 3 speech bubbles in Chinese text: “出发啦，去东京!”, “好困啊...”, and “软萌萌”.

Panel 2, top right: Title text: “{argument name="second panel title" default="TOKYO, JAPAN"}”. Under it, two label strips: “(4-HOUR LAYOVER)” and “4 HOURS”. Interior airport waiting area with large windows, runway and airplane outside, blue seats, passengers in the background, and a duty-free shop on the right with a sign containing Japanese/Chinese-style characters above “DUTY FREE”. Add a dark airport sign with airplane icon reading “TOKYO NRT”. The leather-jacket parent sits with a coffee while the red-scarf duckling sleeps under a blue star-patterned blanket, with the pink-bow duckling nearby holding plush toys. Include exactly 2 speech bubbles: “Zzz...” and “软萌萌”.

Panel 3, bottom left: Title text: “{argument name="third panel title" default="CALGARY, CANADA"}”. Under it, two label strips: “(5-HOUR LAYOVER)” and “5 HOURS WAIT”. Airport lounge with large window view of snowy Rocky Mountains, pine forest, a plane on the runway, and a Canadian flag. Add a dark airport sign with airplane icon reading “CALGARY YYC”. The parent stands with orange rolling suitcase while both ducklings look exhausted or crying beside their blue suitcase and plush toys. Include exactly 1 speech bubble in Chinese: “旅程太长，好累呀...”.

Panel 4, bottom right: Title text: “{argument name="final panel title" default="REUNION IN HOUSTON!"}”. Add a label strip: “ARRIVALS”. Bright airport arrivals area in Houston with palm trees and city skyline visible through large windows. Add a dark airport sign with airplane icon and two lines: “HOUSTON IAH” and “ARRIVALS”. Show an emotional family reunion: the leather-jacket parent hugs the second larger parent duck, both smiling with happy tears, while the two ducklings gather around them with luggage and plush toys. Include a framed family photo on a small table at the right. Include exactly 2 speech bubbles in Chinese: “你们终于到了！想死你们了！” and “终于可以去睡觉了...”.

Text and style constraints: Keep all visible English titles and airport labels crisp and legible, preserve the Chinese speech bubble text exactly as written, use hand-lettered comic typography, no photorealism, no extra panels, no extra main characters, no watermark.

Create a highly realistic studio portrait of {argument name="subject" default="a young East Asian woman"} from the chest up, centered in a vertical 2:3 frame. She has {argument name="hair color and style" default="messy shoulder-length black bob hair with loose flyaway strands"}, with a few fine strands crossing her face and lips as if moved by a soft breeze. Her expression is calm and slightly wistful, lips gently parted, warm brown eyes looking directly at the camera, natural dewy skin, minimal makeup with soft rose lips and subtly defined brows. She wears {argument name="outfit" default="a black ribbed turtleneck sweater"} with visible knit texture and a high folded collar. Use {argument name="lighting" default="soft diffused studio lighting from the upper left"}, gentle shadows, shallow depth of field, and a warm beige seamless background. The composition should feel intimate, elegant, and cinematic, with natural skin texture, realistic hair detail, muted warm tones, no jewelry, no text, no watermark, and no exaggerated retouching.

Create a polished anime-style illustration of {argument name="character name" default="Muumuu Bell"}, a cute cow-themed young woman shopping in a warm Japanese tableware store. She stands in the foreground slightly right of center, holding one floral ceramic plate in her left hand and a small golden hand bell near her mouth with her right hand, looking surprised and curious with parted lips and amber-brown eyes. She has very long flowing {argument name="hair color" default="silvery white hair fading to pale aqua at the tips"}, soft bangs, small tan cow horns, black-and-white cow ears, and a thin cow tail with a black tuft curling at the lower right. Her outfit is a white cow-print sleeveless crop top, a pale pleated skirt, and an oversized black varsity jacket slipped off the shoulders, with striped cuffs and decorative gold script on one sleeve. The store background is softly blurred but detailed: wooden shelving filled with neatly displayed ceramic plates, bowls, mugs, and stacked dishes, all with delicate pastel floral patterns; exactly three prominent shop signs are visible, including a dark chalkboard sign on the upper left with Japanese text and pink flowers reading {argument name="chalkboard text" default="毎日の食卓を もっと素敵に。"}, a small shelf sign reading {argument name="small sign text" default="洋食器の日 7月12日"}, and a large banner in the back reading {argument name="banner text" default="洋食器フェア 特別価格でご提供"}. Add a small white handwritten greeting placard at bottom left reading {argument name="greeting text" default="おはよう"}. Use warm indoor lighting, shallow depth of field, soft bokeh ceiling lights, creamy beige and peach tones, delicate linework, high-detail anime rendering, glossy eyes, subtle blush, and a cozy shopping atmosphere. Keep the image as a single character scene with no extra people, no watermark, and no photorealism.

Create a wide 16:9 anime-style comedic illustration set inside a cramped Japanese ramen shop kitchen during a frantic shift. Center foreground: an energetic orange-haired girl with twin ponytails and glowing amber eyes, wearing a black T-shirt with large white Japanese lettering 「糖質」, jeans, and a worn brown waist apron, aggressively performing noodle draining with a wire noodle strainer; instead of noodles, the strainer contains dessert-like sweets including a slice of strawberry shortcake, and water splashes dramatically in an arc. Her expression is hot-blooded, intense, and shouting, with sweat drops and dynamic motion lines. Left side: a lavender-haired girl with glasses, tired blank expression, black shirt, jeans, sneakers, and a brown apron, reluctantly carrying an absurdly tall stack of ramen bowls; add a speech bubble above her with {argument name="left speech bubble" default="元アイドルです。"}. Right side at the customer counter: a petite blonde girl in a black beret and black shirt holds a ramen bowl topped with strawberry shortcake and pudding-like desserts, looking surprised; add a speech bubble above her with {argument name="right speech bubble" default="アイドルよね?"}. Include exactly 3 visible characters: the energetic orange-haired cook in the center, the reluctant lavender-haired helper on the left, and the surprised blonde customer on the right. Include exactly 2 speech bubbles, one above the left helper and one above the right customer. Include exactly 2 dessert ramen bowls: one in the wire strainer and one held by the blonde customer. Environment details: stainless steel counter and sinks in the foreground, huge boiling ramen pots on the left, shelves with stacked bowls, hanging paper lanterns, blue noren curtains with partial Japanese kana, chopsticks and condiment bottles on the right counter, warm restaurant lighting, compact perspective with depth. Style: polished Japanese anime key visual, crisp line art, vibrant colors, expressive faces, exaggerated comedy, water droplets frozen in motion, dynamic low-to-mid camera angle, highly detailed background but readable composition. Use {argument name="main character hair color" default="orange"} for the central cook, {argument name="shop setting" default="small Japanese ramen shop kitchen"}, and {argument name="central shirt text" default="糖質"}. Avoid photorealism, avoid extra characters, avoid changing the count of bowls, speech bubbles, or main subjects.

Create a monochrome manga-style illustration of two elegant androgynous young men standing back-to-back in a refined fashion portrait. The left figure is taller, shown from mid-thigh up in a white suit jacket over a dark shirt and tie, with long pale hair tied in a low ponytail and loose bangs covering one eye; he holds an open ornate folding fan in front of his mouth and nose, the fan decorated with floral patterns, lace-like black edging, and a single large eye motif near the center. The right figure is slightly shorter, wearing a glossy black suit jacket with a white shirt and dark tie, with tousled pale wavy hair tied into a small low ponytail; he turns his face toward the viewer with delicate lashes and a calm, mysterious expression while adjusting or holding one wrist with slim elegant hands. Use fine black-and-white ink linework, soft grayscale shading, intricate hair strands, delicate facial features, high-fashion gothic elegance, subtle paper texture, and a clean off-white background with a thin double-line rectangular border near the edges. Keep the composition tightly framed, centered, balanced, and text-free, with exactly two characters and one visible folding fan. Allow the figures’ pale hair to remain mostly white with fine graphite shading. Character mood: poised, secretive, beautiful, slightly melancholic. Optional customization: make the left figure’s suit {argument name="left suit color" default="white"}, the right figure’s suit {argument name="right suit color" default="black"}, the characters’ hair {argument name="hair color" default="pale platinum blonde"}, and the fan motif {argument name="fan motif" default="floral pattern with a single large eye"}.

Goal: Create a vertical Japanese educational infographic summarizing {argument name="headline text" default="切り花に炭酸飲料を入れる方法とメリット・デメリットまとめ"}, explaining how to add carbonated soft drinks to cut flower vase water, with benefits, drawbacks, recommended dilution, procedure, and better basic care methods.

Canvas: Portrait 4:5 infographic, clean magazine-style layout on a warm off-white background, soft pastel borders, rounded information cards, subtle shadows, friendly household gardening aesthetic. Use a balanced mix of flat vector icons and small realistic photo panels. Main colors: coral pink, chocolate brown, mint green, pale yellow, sky blue, and light gray.

Top header: Large bold Japanese headline in two colors, with the phrase about carbonated drinks emphasized in coral pink and the rest in dark brown. Under it, add a smaller green subtitle: {argument name="subtitle text" default="海外で話題の「花を長持ちさせる裏技」を正しく知って、きれいなお花を長く楽しみましょう。"}. On the upper right, place a realistic photo-style bouquet in a clear glass vase on a wooden table, with pink gerbera daisies, cream roses, small white filler flowers, and greenery. Beside it show exactly 2 drink bottles/cans: one red cola can labeled “COLA” and one blue cider bottle labeled “CIDER”. Below them show exactly 2 small vertical photo panels of vase water: one clear water close-up and one brown/tinted water close-up.

Main upper content area: Use exactly 2 side-by-side rounded cards.
Card 1, left, pale yellow title bar: title text {argument name="benefits section title" default="なぜ炭酸飲料で花が長持ちする言われるの？"}. Include exactly 2 numbered benefit rows with pink circular number badges: 1) “糖分が栄養になる” with a simple icon of stacked sugar cubes, and explanatory small text saying sugar in soda may be used as flower energy; 2) “酸性成分が働く” with a blue water drop icon, and small text saying acidity may help water uptake.
Card 2, right, pale pink title bar with a yellow warning triangle icon: title “知っておきたいデメリット・注意点”. Include exactly 4 warning rows, each with a red X icon: 1) sugar can encourage miscellaneous bacteria and make stems rot; 2) water becomes cloudy easily and looks bad; 3) dark-colored drinks such as cola can color the water and reduce visual beauty; 4) too much can have the opposite effect because excessive concentration may worsen water uptake and cause wilting. Keep text concise and Japanese.

Middle blue instruction band: Create one wide rounded rectangle with a blue outline and pale blue fill. Divide into two columns.
Left column title: “炭酸飲料の入れ方（おすすめの割合）”. Include a blue circular label “おすすめの割合” and a large formula: “炭酸飲料：水 = 1：10 ～ 1：20程度”, with small example text “例：水1リットルに炭酸飲料50〜100ml”. Add a “ポイント” subsection with exactly 2 checkmark bullet points: use clear cider/soda without artificial color when possible; dark drinks such as cola can color the water even in small amounts.
Right column title: “手順”. Include exactly 4 numbered steps in blue circles: 1) put clean water in the vase; 2) add carbonated drink at the above ratio; 3) mix lightly; 4) arrange cut flowers. Add a pale yellow note box: “水はこまめに交換しましょう（できれば毎日）”. On the far right add a large simple equation illustration: water drop icon labeled “水” plus a glass with bubbly yellow liquid labeled “炭酸飲料”.

Lower green care section: A wide rounded rectangle with a green header title: {argument name="care section title" default="切り花を長持ちさせる基本のお手入れ（炭酸飲料より効果的！）"}. Inside, show exactly 4 equal care cards in a row, each with a green numbered circle, a short Japanese title, a realistic photo thumbnail, explanatory text, and a green “ポイント” label. The 4 cards must be: 1) “茎を斜めに切り戻す”, photo of a hand cutting a green stem diagonally with a knife, explain better water absorption and freshness, point: cut underwater to prevent air entry; 2) “こまめに水替え”, photo of water being poured into a glass vase, explain changing water daily or every 1–2 days, point: recut stems when changing water; 3) “葉が水に浸からないようにする”, photo of stems and leaves inside a vase, explain submerged leaves rot and cause bacteria, point: remove leaves below the waterline and improve ventilation; 4) “市販の延命剤を使う”, photo of a blue flower food packet near a vase, explain it contains nutrients and antibacterial ingredients, point: follow product instructions.

Bottom summary strip: Use two rounded boxes. Left larger pale pink box with label “まとめ”, a small flower icon, and text explaining that carbonated drinks may support flower longevity when used at the proper concentration, but thorough basic care is the most important secret. Right smaller pale pink advice box with label “一言アドバイス”, small vase-and-flower icon, and text advising to avoid direct sunlight and air-conditioner wind, and keep flowers in a cool place.

Style constraints: Japanese typography must be legible, friendly, and bold for headings; use clean grid alignment and generous spacing. Do not add extra sections or extra repeated items beyond the specified counts. Avoid watermark, QR code, people, or brand logos other than the simple “COLA” and “CIDER” labels.

Create a photorealistic lifestyle portrait of an adult {argument name="subject description" default="young East Asian woman"} lying on a bed in soft morning sunlight, viewed from a slightly elevated overhead angle like an intimate candid smartphone photo. She has {argument name="hair color and style" default="short layered blonde hair with wispy bangs"}, fair skin, minimal natural makeup, and a calm thoughtful expression while gazing off to the side. Her right hand rests lightly near her lips and chin, and her left arm is bent above her head on the pillow. She wears a simple {argument name="shirt" default="plain slightly wrinkled white T-shirt"}. The setting is a bright minimalist bedroom with exactly 2 white pillows, white bedding, and a sunlit window on the right with sheer white curtains; warm light creates realistic highlights on her hair, face, arm, and shirt, with gentle shadows and soft fabric texture. Use a close crop from head to mid-torso, natural skin detail, shallow depth of field, subtle lens distortion, realistic color grading, no visible text, no jewelry, no exaggerated posing, no watermark.

Create a realistic vertical outdoor portrait photo of a young East Asian woman with {argument name="hair color" default="long dark brown-black hair with soft bangs"} crouching beside a wooden park bench on a paved walkway. She has a delicate oval face, fair skin, subtle natural makeup, soft pink lips, and a calm slightly wistful expression while looking directly at the camera. She wears a sleeveless cream lace-trimmed top with small colorful floral embroidery, a short layered white ruffled skirt, white low-heeled strappy sandals, and a beige woven straw shoulder bag with a long braided strap hanging at her side. Her pose is low and compact, knees bent, arms extended downward with relaxed hands near the ground. The bench sits diagonally along the left side with dark wooden slats and metal supports, and the path recedes into a green leafy park background on the right. Use bright natural summer daylight with dappled shadows from trees, shallow depth of field, soft bokeh foliage, crisp facial detail, realistic skin texture, and a gentle fashion-magazine photography style. No text, no watermark, no extra people, no distorted hands or feet.

Goal: Create a dense Japanese infographic ranking {argument name="topic" default="AI image generation tools"} as a 2026 tier list, with a premium black, navy, and gold tech aesthetic, designed for social media sharing.

Canvas: Square 1:1 poster, high resolution, dark black background with subtle blue grid lines and glowing cyan/gold accents. Use bold Japanese typography, sharp table borders, star ratings, crowns, badges, and app-logo style icons. Overall look should feel like a professional comparison chart made after extensive testing.

Header: Large title at top: 「AI画像生成ツール Tier表」 with “AI” and Japanese text in white, “Tier表” in gold. Add a gold badge on the upper left reading 「2026年 最新版」. Above the title, add the small line 「保存必須！迷ったらこれを見ればOK」. Under the title, add a blue outlined subtitle bar: 「用途別に最強が一目でわかる 完全ガイド」. Add a small gold crown near the title.

Top-right selection box: Add a bordered panel titled 「選び方のポイント」 with exactly 4 checkbox bullet items: 「何を作りたいかで選ぶ」, 「得意・不得意を理解する」, 「目的に合わせて使い分ける」, 「迷ったら上位から試す」.

Main layout: A large comparison table fills most of the image. Left side has tier bands, middle has ranked tool rows, right side has star-rating columns and price notes. Use exact tier groups: SSS 「圧倒的最強」, SS 「非常に優秀」, S 「優秀」, A 「特化型で強力」, B 「用途次第で活躍」. Use large tier letters in gold, cyan, green, purple, and pale blue respectively.

Main table rows: Include exactly 8 ranked tools, each with a circular rank medal, a square logo icon, a tool name, a short Japanese description, and several small colored feature tags. The rows are:
1. {argument name="top ranked tool" default="GPT Image 2"} — description 「総合力No.1の最強モデル」, logo resembling the OpenAI knot mark, rank medal gold with “NEW” label.
2. Seedream 5.0 Pro — description 「広告・商用クリエイティブ最強」, blue spiral logo.
3. Nano Banana — description 「リアル写真・人物・商品に最強」, yellow banana logo.
4. Muse — description 「映画のような世界観・コンセプトアート」, purple M logo.
5. Ideogram — description 「文字デザイン・タイポグラフィ最強」, black abstract brain/typography logo.
6. Flux — description 「イラスト・アート・CG表現が得意」, blue triangular Flux logo.
7. Recraft — description 「ロゴ・アイコン・ベクターに最強」, black-and-white R-like logo.
8. Imagen 2 — description 「自然風景・写真の再現に強い」, multicolor Google G logo.

Rating columns: Use exactly 8 comparison columns with Japanese labels: 「総合力」, 「リアル/人物」, 「イラスト/アート」, 「文字/デザイン」, 「編集/加工」, 「商用利用」, 「使いやすさ」, 「料金目安(月額)」. Fill each row with gold star ratings, including half/empty stars where appropriate, and compact monthly pricing notes in the final column. Keep the table legible but information-dense.

Bottom section: Add a horizontal “best by use case” guide titled 「用途別 最強早見表」. Include exactly 7 crowned cards, each with a number, category, logo, tool name, and short verdict:
1. 「リアル人物」 — Nano Banana — 「圧倒的リアル」.
2. 「広告・商用」 — Seedream 5.0 Pro — 「商用品質No.1」.
3. 「総合力」 — GPT Image 2 — 「なんでも高水準」.
4. 「シネマ・世界観」 — Muse — 「映画レベル」.
5. 「文字・デザイン」 — Ideogram — 「文字が綺麗」.
6. 「イラスト・アート」 — Flux — 「アート表現が得意」.
7. 「ロゴ・アイコン」 — Recraft — 「ベクター最強」.

Bottom-right recommendation box: Add a glowing panel titled 「迷ったらこれ！」 with a lightbulb icon and the message 「まずは上位から 3つ使えば ほぼ全てカバーできる！」.

Footer: Add two dark bordered note boxes. Left box with target icon and two bullet notes: 「1つのツールにこだわらず、目的に合わせて使い分けるのが最強の戦略！」 and 「プロほど複数のツールを組み合わせて、クオリティを最大化しています。」 Right box with bookmark icon and text: 「保存して、いつでも見返せるようにしよう！」 and 「アップデートされたらまた最新版に更新します！」 Include a tiny disclaimer line about pricing and ratings being estimates as of 2026.

Visual style: Sleek cyber dashboard, black glass panels, thin neon blue dividers, gold highlights, dense but organized layout, crisp Japanese text, app icons in white rounded squares, star ratings in metallic gold, no photographic background, no people.

Constraints: Preserve the exact count of 8 ranked tools, 5 tier bands, 8 rating columns, 4 selection tips, and 7 bottom use-case cards. Make all text sharp and readable. Do not add extra tools, extra cards, watermarks, or random English labels.

Create a tall vertical gothic-romantic anime illustration in an ornate European palace music room, using a refined sepia monochrome palette with warm candlelight, strong dark ink-like outlines, intricate linework, and a slightly simplified but highly elegant manga rendering style. Show exactly 3 beautiful young male musicians: the central figure is {argument name="central musician" default="a tall black-haired violinist"}, standing full body in the foreground from a slightly high camera angle, wearing a long black formal tailcoat with layered vest, tie, chains, jeweled brooches, fitted trousers, and polished boots, playing a violin with bow held diagonally across his body; at lower left is {argument name="left musician" default="a pale curly-haired guitarist"} seated on an ornate chair, holding an acoustic guitar; at right is {argument name="right musician" default="a pale wavy-haired pianist"} seated at a glossy grand piano, hands on the keys, wearing a light formal suit. Set them inside a lavish baroque room with towering arched windows on the left, heavy draped curtains, carved wall panels, floral wall art in a gilded frame, crystal chandelier overhead, candelabras with lit candles, vases of flowers, ornate chairs, reflective patterned marble floor, and blurred foreground flowers near the bottom edge. Emphasize dramatic chiaroscuro, delicate sparkles on jewelry and instruments, soft dust motes, elegant melancholic expressions, aristocratic atmosphere, and dense decorative detail without modern objects, text, logos, or bright colors. Use {argument name="aspect ratio" default="9:16 vertical"} composition, cinematic depth, and poster-quality detail.

Goal: Create a richly detailed anime fantasy marketplace scene celebrating {argument name="headline text" default="Knife Day"} with Japanese poster-style typography and a knife merchant stall.

Canvas: Wide 16:9 illustration, warm cinematic lighting, high-detail painterly anime style, dusty outdoor bazaar under beige cloth awnings, sunbeams and haze in the background, earthy browns, ochres, leather, wood, and muted metal highlights.

Layout: The central focus is a young cat-eared female merchant standing behind a wooden counter full of knives. Place large Japanese event text in the upper left, a speech bubble near the merchant’s head, a wooden shop sign on the right wall, a nameplate sign on the front of the stall, and three small product-description placards along the counter. Two customers are seen from behind in the foreground left and right, with a partial third blond head at the bottom right edge.

Subject details: The merchant is {argument name="character name" default="Jeannette"}, a small serious-looking beastkin/anime girl with fluffy tan cat ears, short messy ash-blond hair, amber eyes, and a calm businesslike expression. She wears a dark brown adventurer coat with belts and straps, black gloves, and a deep red scarf. She holds a small knife upright in her right hand and gestures with her left palm open. Behind her is an oversized traveler’s backpack packed with tools, sheathed blades, rolled gear, red and green glass flasks, and a large sword or blade rising over her shoulder.

Foreground customers: Include exactly 3 visible customers: 1 dark-haired male adventurer on the left with a green cloak, backpack, and sword hilt over his shoulder; 1 red-haired male adventurer on the right with a dark headband and armor visible from behind; 1 partial blond-haired person at the lower right edge, only the head and shoulder visible.

Knife display: Show exactly 18 distinct knives/blades laid out across the front counter, varying in size and type: practical utility knives, hunting knives, survival knives, daggers, folding knives, a cleaver-like blade, and several ancient-style blades. They should rest on leather rolls and wooden boards, with realistic metal reflections and worn handles.

Text content: Use visible Japanese calligraphy/handwritten signage. Upper left main text should read “7月12日” and “ナイフの日”, with the subtitle “切れ味は、信頼の証。” A speech bubble near the merchant should read “用途と予算を言ってくれれば、合うものを選ぶ。” The central nameplate should introduce the merchant, reading “旅商人「ジャム」こと ジェメット 道具と情報の専門家。ハイエナ族の旅商人。” On the right wooden shop board, include two sections: “買います” with “遺跡の品・素材・情報”, and “売ります” with “道具・薬・地図・その他いろいろ”, ending with “相談は無料だ。気軽にどうぞ。” Product placards on the counter must be exactly 3: left “実用ナイフ 日用品から戦闘用まで 各種取り揃え。” center “サバイバルナイフ 過酷な環境を生き抜く 冒険者の必需品。” right “古代文明の刃 切れ味は現代を超える。が、売れにくい。”

Visual style: Detailed Japanese light-novel/anime illustration, semi-realistic props, sharp linework with painterly shading, warm backlight, soft atmospheric depth, believable clutter, parchment signage, no modern objects. Keep the composition readable like an event poster while preserving the lively market-stall narrative.

Create an ultra-detailed high fantasy cinematic illustration of {argument name="character name" default="the Serpent Queen"}, a regal pale-skinned queen with very long flowing {argument name="hair color" default="silver-white hair"}, wearing a jeweled gold crown and an ornate translucent {argument name="dress color" default="deep crimson"} gown covered in intricate gold filigree, chains, scales, embroidery, and layered sheer fabric. She stands in a powerful contrapposto pose in the foreground, looking slightly upward and to the left with a calm imperious expression, one leg visible through a high slit, gold jewelry wrapping her arms and legs. Beside her is exactly 1 enormous white serpent, coiled in the lower right foreground with its raised head near her waist, pearl-like scales, golden ornamental harness details, and a poised protective expression. Behind them are exactly 3 prominent armored royal guards in white-and-gold plate armor with helmets and capes: 1 central guard directly behind the serpent, 1 guard to the right, and 1 partially visible guard to the left. Include exactly 3 prominent crimson royal banners with gold eagle-like emblems, flowing in the wind: 1 large banner on the right, 1 mid-distance banner on the left, and 1 smaller banner farther left. Set the scene before a vast luminous {argument name="castle style" default="white Gothic cathedral-palace"} with towering spires, arches, carved stone, balconies, and ceremonial grandeur. The atmosphere is bright daylight with soft haze, windblown hair and fabric, drifting red flower petals, pale stone courtyard, and a sense of imperial procession. Style: highly polished fantasy concept art, ornate baroque detail, realistic anatomy, ethereal lighting, ivory and gold palette contrasted with crimson, dramatic low-angle composition, sharp foreground detail, grand scale, no text, no watermark, no modern objects.

Goal: Create a high-resolution French promotional social media banner for the public transport app {argument name="app name" default="13enBus"}, announcing its iPhone availability in a polished advertising style.

Canvas: Wide horizontal 16:9 banner, approximately 1200×675 px. Use a bright Mediterranean outdoor setting with a shallow-depth-of-field background: blue sky, blurred green valley, distant rocky mountain, and a sunny road with a bus stop shelter on the right.

Layout: On the left, place a large bold headline in French with strong contrast: “13enBus —” in bright blue followed by “Enfin sur iPhone !” in large white text, with a green apple emoji beside it. Under it, add the subtitle “Vos bus en temps réel à Trets et dans la vallée” in white. In the center foreground, show a realistic hand holding a modern black iPhone vertically. On the phone screen, display a clean app onboarding screen with a small transit card, the heading “Vos prochains bus, en un coup d'œil.”, a blue “Suivant” button, and tiny app interface details. A red arrow points from the right toward the phone’s small transit card, highlighting a circled waiting time.

Main subject details: The phone screen should include exactly 1 small transit card with exactly 3 visible bus rows: line 15 “Château-Gombert” with “2 min” emphasized in a red circle, line 15 “Auriol” with “7 min”, and line 85 “Les Caillols” with “8 min”. Behind the phone on the right, place exactly 1 realistic white-and-blue city bus driving on the road, front facing slightly toward the viewer, with route number 13 visible on its sign.

Feature callouts: On the right side, stack exactly 3 rounded white pill-shaped feature boxes with blue circular icons on the left and bold black French text. The 3 boxes are: 1) yellow bell icon, “Alarmes de station anti-retard”; 2) yellow warning triangle icon, “Suivi des déviations et travaux”; 3) Instagram-style gradient camera icon, “Infos trafic sur Insta : {argument name="instagram handle" default="@13enbus"}”.

Bottom banner: Add a full-width red strip along the bottom with a small “100% GRATUIT” badge at the far left and large white uppercase text: “100% GRATUIT & SANS INSCRIPTION | DISPONIBLE SUR APP STORE & GOOGLE PLAY”.

Visual style: Realistic HD advertising composite, crisp typography, saturated colors, strong sunlight, professional app launch campaign design. Use clean French transit-app branding with blue, white, red, and green accents. Keep the phone and text sharp while the background remains softly blurred.

Constraints: Use exactly the described 3 feature callouts, exactly 1 phone, exactly 1 hand, exactly 1 bus, exactly 1 bottom red banner, and exactly 1 green apple emoji. No extra logos, no watermark, no additional unrelated text.

Create a realistic high-quality cosplay photograph in a grand medieval academy hall inspired by fantasy anime. Show exactly two young women in matching noble knight uniforms: the foreground character is {argument name="foreground character" default="Angelica"}, a slim young woman with pale skin, light blue hair in a high ponytail with long face-framing bangs, blue eyes, and a calm serious expression; she stands in a heroic fencing pose, body turned three-quarters left, right arm extended toward the camera holding one polished rapier diagonally across the frame, left gloved hand lowered. Her costume is a navy blue long military-style dress with gold piping, black gloves, brown leather belt and side straps, a gold-brown cloak flowing over her shoulders, and a shiny silver chest breastplate with ornate filigree. Behind her stands exactly one second character, {argument name="background character" default="Rozemyne"}, slightly out of focus, a petite young woman with long deep blue hair, wearing a similar navy dress with gold trim and a gold-brown cloak, hands clasped at her chest, watching with a gentle concerned expression. The setting is a bright stone cathedral-like library or academy corridor with tall columns, large soft window light, and one dark blue hanging banner in the background showing a gold open-book emblem surrounded by laurel leaves. Use cinematic shallow depth of field, natural skin texture, realistic fabric and metal reflections, soft daylight, elegant composition, vertical 4:5 framing, no text overlay, no watermark, no extra characters, and no extra weapons.

Create a warm hand-drawn digital illustration of recursive image generation inception, showing a cute anthropomorphic raccoon creator at a wooden desk using GPT Image 2 on a laptop. The scene is in a cozy studio with beige paper-textured background, inked outlines, soft shading, muted earth tones, and orange accent highlights. In the foreground, place 1 large raccoon character wearing a black hoodie with an orange mountain-and-flag logo on the back, sitting at the laptop and pointing excitedly at the screen with an open-mouthed smile. Add a speech bubble above the raccoon that reads “IMAGE GENERATION” in black and “INCEPTION” in orange, with a small orange sparkle beneath. On the laptop screen, show the GPT Image 2 interface with the header “GPT Image 2” and an infinite nested recursion of the same scene: exactly 6 visible screen/laptop frames receding inward, each smaller and perspective-aligned, creating a tunnel effect. Inside the main visible screen, include exactly 6 main animal characters seated side by side at desks: 1 raccoon in a black hoodie, 1 panda in a green hoodie, 1 orange fox in a blue hoodie, 1 hedgehog in a yellow hoodie, 1 small purple animal, and 1 tiny nested animal inside the deepest screen. Add motivational posters in the recursive room backgrounds with short text such as “FOCUS BUILD SHIP,” “KEEP IT SIMPLE,” “MAKE COOL THINGS,” and “CREATE EVERY DAY.” At the bottom of the laptop interface, include a prompt input field reading “What do you want to create?” and an orange button labeled “Generate,” plus two small outline action icons. On the desk, include exactly 3 prominent accessories: a black mug with a white X logo on the right, a spiral notebook reading “ENDLESS CREATIVITY” with an orange heart below it, and two black pens with orange accents. Add a leafy green plant at the far left edge and another plant visible inside the recursive screen room. Use a slightly wide 4:3 composition, dynamic perspective looking over the raccoon’s shoulder, playful creator-community mood, crisp readable text, no photorealism, no watermark. Use {argument name="app name" default="GPT Image 2"}, {argument name="speech bubble text" default="IMAGE GENERATION INCEPTION"}, {argument name="button label" default="Generate"}, {argument name="notebook text" default="ENDLESS CREATIVITY"}, and {argument name="main character" default="anthropomorphic raccoon creator"}.

Goal: Create a bright vertical travel vlog thumbnail/collage featuring a smiling young woman traveler in a sunny outdoor alley, surrounded by cute scrapbook stickers and hand-drawn doodles.

Canvas: Vertical 3:4 social media image, high-resolution, warm daylight, shallow depth of field. Background is a charming pedestrian street or café alley with plants, terracotta umbrellas, soft bokeh, and a small chalkboard sign in the distance.

Main subject: A cheerful {argument name="character description" default="young East Asian woman with shoulder-length black hair and bangs"} stands slightly right of center, turned three-quarters toward the camera, smiling warmly. She wears a loose white T-shirt with a small nature print on the chest, light blue jeans, and a large beige backpack over one shoulder. Add a cute plush keychain hanging from the backpack. Put a thick white cutout outline around the subject, like a sticker.

Layout and text stickers: Use exactly 6 main text stickers: 1) large top-left title reading {argument name="main title" default="Travel Vlog"} in oversized rounded pastel bubble letters with a thick white border; 2) top-right stacked sticker reading {argument name="top right phrase" default="Good Vibes Only"} with a yellow heart and yellow smiley face; 3) small pink ribbon banner on the left reading {argument name="banner text" default="let's go!"}; 4) dark cloud speech bubble on the right reading "explore more" with a small pink heart; 5) bottom-left sticker reading "on the way" in playful blue and pink bubble letters with a small white flower; 6) bottom-right sticky note reading {argument name="note text" default="Collect moments not things"} with a pink tape strip and a small heart.

Decorative elements: Include exactly 3 illustrated travel icons: a cute line-art camera with a heart on the lens on the left, a folded map with a pink location pin on the lower right, and the backpack plush charm. Add multiple small white hand-drawn sparkles, arrows, hearts, squiggles, and doodle marks scattered around the subject, keeping them light and airy.

Visual style: Photorealistic lifestyle portrait blended with kawaii sticker graphics, pastel colors, glossy scrapbook aesthetic, soft white outlines, playful vlog thumbnail design, warm golden sunlight, cheerful vacation mood.

Constraints: Keep all text legible and in English, preserve the exact 6 main text stickers and 3 illustrated travel icons, avoid extra large words, avoid watermarks or logos, and make the subject the clear focal point.

Create an ultra-premium executive studio portrait of {argument name="subject" default="a young Black man"} seated in a black leather armchair, centered and facing the camera with a calm, confident, serious expression. He wears a perfectly tailored all-black double-breasted suit, black dress shirt, textured black tie, black socks, polished black Oxford shoes, a slim white pocket square, and a luxury dark wristwatch on his left wrist. Pose him with legs crossed, both arms relaxed on the chair arms, upright posture, shoulders squared, direct eye contact. Use a vertical 2:3 composition, full seated body visible from head to shoes, symmetrical framing, slight low-to-eye-level perspective. Background is a seamless dark charcoal studio backdrop with subtle vignette and no props besides the chair. Lighting should be dramatic high-end editorial portrait lighting: large soft key light from front-left, gentle fill from front-right, subtle rim separation on shoulders, controlled highlights on the leather chair and shoes, deep rich blacks with visible fabric texture. Photorealistic, sharp focus on face, natural skin texture, premium magazine cover quality, refined contrast, cinematic grading, no text, no watermark, no distorted hands, no extra fingers, no facial stylization.

Goal: Create a full-color manga double-page spread in the style of a dramatic shonen battle scene, resembling a French-translated One Piece chapter page, with heavy black panel borders, dynamic action, expressive hand-lettered sound effects, and saturated blue-red cinematic coloring.

Canvas: Landscape 4:3 comic page collage, approximately 1024×768, with a white gutter grid separating panels. The image should look like a restored and colorized manga scan: inked line art, painterly digital color, high contrast shadows, and slightly gritty paper texture.

Layout: Use exactly 14 visible comic panels arranged as a dense two-page spread. Left side contains 8 panels: 3 small panels across the top, 4 narrow action panels beneath them, and 1 large dramatic panel at the bottom. Right side contains 6 panels: 1 huge blue forest panel at the top right and 5 smaller panels along the bottom right, including two thin stacked panels on the left, one vertical center panel, one large right panel, and small speech-bubble areas integrated into the right panel.

Subject details: Show {argument name="hero character" default="a white-haired rubbery warrior with flame-like hair, round eyes, a huge grin, and cartoonish Gear Five energy"} fighting {argument name="villain character" default="a massive horned dragon-like emperor with long white hair, black shadowed armor, and an enormous spiked club"}. The scene alternates between close-ups of the hero’s manic smiling face, explosive attacks, and a vast blue forest battlefield. The hero appears glowing and elastic, with pale skin, swirling white hair, and exaggerated anime expressions. The villain is towering, menacing, mostly dark purple and black, with horns, flowing hair, and a brutal silhouette.

Panel-by-panel content count: Panel 1, top-left small: close-up of the grinning flame-haired hero saying “HEIN ?!” with orange fire lighting. Panel 2, top row middle: white speech bubble reading “…QUE TU N’ES PAS JOY BOY !” against pale blue motion energy. Panel 3, top row right: glowing blue-white impact sphere with speed lines and a speech bubble reading “MU SAIT PARFAI-TEMENT…”. Panel 4, second row far left: red-brown motion panel with distorted ground or body and large vertical sound effects. Panel 5, second row narrow: red beam-like action panel with a tiny speech bubble reading “ALLONS-Y !”. Panel 6, second row center: close-up of the hero’s wild grin framed by huge black Japanese sound effect lettering. Panel 7, second row right: dark close-up of a single intense eye in purple shadow. Panel 8, bottom-left large: the hero hangs injured or limp in front of the towering horned villain holding a club, red smoky sky behind them, with two large speech bubbles reading “…N’ÉTAIT PAS AUSSI FAIBLE…!” and “JOY BOY, LUI…”, plus a small black caption box reading “LE ROI DU MONDE DANS TOUTE SA SPLENDEUR…!!”. Panel 9, top-right huge: immense blue enchanted forest vortex, twisted trees, swirling leaves and wind, a black silhouetted warrior at the right edge holding a weapon, and bold black Japanese sound effects; add the watermark {argument name="watermark text" default="@stein_lr"} near the lower-left of this large panel. Panel 10, bottom-right upper-left small: close-up of the hero spinning or rushing downward, speech bubble “PAREIL POUR MOI !”. Panel 11, bottom-right lower-left small: narrow vertical impact panel with a falling figure, blue explosion, and a small empty or dotted speech bubble. Panel 12, bottom-right center vertical: blue sky and dead trees with a flaming projectile streaking diagonally, speech bubble reading “MU Y VOIT PLUS CLAIR DÉSORMAIS !”. Panel 13, bottom-right large: the hero spinning like a pale tornado above a dried forest, blue spiral energy and falling debris, speech bubbles reading “LA FORÊT S’EST DES-SÉCHÉE !”, “HEIN ??”, and “!!?”. Panel 14, embedded small speech region near the right edge: preserve the sharp white bubble with “!!?” as part of the large action panel composition.

Text style: Use French uppercase manga lettering in thick irregular black font inside white speech bubbles with black outlines. Use multiple oversized black Japanese-style sound effects, especially around impacts and motion. Keep all visible text legible but hand-drawn.

Color and mood: Left page should be dominated by fiery oranges, reds, smoky browns, and black shadows. Right page should be dominated by icy blues, navy, cyan highlights, pale moonlit whites, and black silhouettes. Strong contrast between warm villain confrontation and cold supernatural forest vortex.

Constraints: Preserve the exact 14-panel count and the described panel arrangement. Do not add extra characters beyond the hero, villain, silhouettes, and tiny action figures implied by the panels. Keep thick manga panel gutters, dramatic perspective, dense speed lines, painterly colorization, and no modern UI elements.